Construction and Validation of Risk Predictive Model for Cognitive Impairment in Adult Congenital Heart Disease
MA Dandan
HUO Xiaowei
PENG Na
YANG Miao
Abstract：Objective To construct risk predictive model for cognitive impairment in adult congenital heart disease(ACHD)and to validate its predictive efficacy.Methods A total of 558 ACHD patients admitted to the author's hospital from January 2023 to February 2024 were enrolled as study subjects by convenience sampling method.The patients were divided into modeling group(n=390)and validation group(n=168)at 7∶3 ratio.The self-designed general information questionnaire,self-rating anxiety scale(SAS),self-rating depression scale(SDS),Montreal congition assessment(Mo-CA)were used to collect data,the influencing factors were screened through Logistic regression analysis,R software was employed to construct nomogram predictive model,and its predictive performance was subsequently validated.Results The incidence of cognitive impairment in 558 ACHD patients was 37.63％.Multivariate Logistic regression analysis re-vealed that age,marital status,body mass index(BMI),disease severity,diabetes mellitus and anxiety were significant influencing factors for cognitive impairment in ACHD patients(P＜0.05).The receiver operating characteristic(ROC)curve showed the area under the curve(AUC)for predicting cognitive impairment in ACHD patients was 0.933,with maximum Youden index of 0.706 and cut-off value of 0.731,the sensitivity and specificity were 79.80％and 90.80％re-spectively.Conclusion The risk predictive model constructed in this study demonstrates good predictability and scientific validity,providing the reference basis for clinical staff to predict cognitive impairment in ACHD patients.
Keywords：Adult congenital heart diseaseCognitive impairmentRisk predictive modelPredictive value
Publication Date：2025-04-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 312-317 )